International Research Journal of Agricultural Economics and Statistics

M. S. Kasture ¹, A. J. Shivagaje ², C. G. Shelake ¹, A. J. Nalavade ²

Affiliations
1 Department of Statistics, New Arts Commerce and Science College, Ahmednagar (M.S.), IN
2 Institute (M.P.K.V.), Rahuri, Ahmednagar (M.S.), IN

Abstract

The present ICT era has changed the scenario of multivariate data or information usage altogether. Organizations treat data as an asset and they try to employ various methodology to come up with organization progress oriented conclusions. A wide range of database tools to manage the huge data and equally number of software’s are also developed to visualize, present and analyses the big data. XLSTAT with diversified data analyzing utilities, is one such tool that can be appended to usual Excel software. The present paper gives an application of Naïve Bayes Classifier applied to a data on Global Super Store Orders-2016 (Source: secondary data obtain from data.world platform). This application will give the insight of understanding the concept of Naive Bayes Classifier. It will also show the effect of continuous data monitoring and maintenance on derived results of Naïve Bayes Classification. The summary of derived output will facilitate the comparison and will also give an idea about the overall trend of the factors under study. The step based analysis of big and diverse data shows that global accuracy of Naïve Bayes Classifier increases with increase in data size.

Keywords

Big Data, Confusion Matrix, Global Accuracy of the Model, Posterior Probability, Regression.

Full Text

     

Ashok J. Shivagaje ¹, Madhukar S. Kasture ¹, C. G. Shelake ¹, A. J. Nalavade ²

Affiliations
1 Department of Statistics, New Arts Commerce and Science College, Ahmednagar (M.S.), IN
2 (M.P.K.V.), Rahuri, Ahmednagar (M.S.), IN

Abstract

Due to the advent of low cost advanced ICT and software availabilities various organizations are creating data ware houses and thereby maintaining large dimensional, multivariate, valuable data as an asset. Therefore, a large number of carrier opportunities in data analysis in the capacity of data scientists are emerging. In order to cope up with the market demand of data scientists, academia are updating their syllabi by introducing various statistical analysis softwares, computer based practical’s and at least one semester project. The objective of this paper is to bring these critical issues to the notice of academies’, researchers and data analysts. The paper also gives discussion regarding resolving these issues. Further, statistical theories and concepts involved in data analysis is thoroughly discussed through a case study in management science. The results of the data analysis in the proposed case study indicates that peoples by and large gives priority of expenditure as food, clothing and shelter. This finding is highly consistent with the basic needs discussed in many economic theories. Further, to achieve the family and personal goals the first priority is given to saving and last to sale of agriculture land.

Keywords

Exploratory, Explanatory, Confirmatory, Data Analysis.

Full Text